Layui

付费应用的分布

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns


add = "C:/Users/lenovo/Desktop/applestore(1).csv"
data = pd.read_csv(add)
print(data.head())

# 可视化付费应用的分布
#fact generator
print ('1. Free apps are ' + str(sum(data.price == 0)))
print ('2. Counting (outliers) super expensive apps ' + str(sum(data.price > 50)))
print (' -  which is around ' + str(sum(data.price > 50)/len(data.price)*100) +
       " % of the total Apps")

#处理掉异常值 价格大于50$的应用
outlier=data[data.price>50][['track_name','price','prime_genre','user_rating']]
freeapps = data[data.price==0]
outlier

# removing
paidapps =data[((data.price<50) & (data.price>0))]
print('Now the max price of any app in new data is : ' + str(max(paidapps.price)))
print('Now the min price of any app in new data is : ' + str(min(paidapps.price)))
#paidapps.prime_genre.value_counts()



plt.style.use('fivethirtyeight')

价格分布与类别的关系


plt.figure(figsize=(15,15))
plt.subplot(2,1,1)

plt.hist(paidapps.price,log=True)
plt.title('Price distribution of apps (Log scale)')
plt.ylabel("Frequency Log scale")
plt.xlabel("Price Distributions in ($) ")

plt.subplot(2,1,2)
plt.title('Visual price distribution')
sns.stripplot(data=paidapps,x='price',orient = 'v' )
plt.show()

yrange = [0,25]
fsize =15

plt.figure(figsize=(15,10))

plt.subplot(4,1,1)
plt.xlim(yrange)
games = paidapps[paidapps.prime_genre=='Games']
sns.stripplot(data=games,x='price',jitter= True , orient ='v',size=6,color='#eb5e66')
plt.title('Games',fontsize=fsize)
plt.xlabel('')

plt.subplot(4,1,2)
plt.xlim(yrange)
ent = paidapps[paidapps.prime_genre=='Entertainment']
sns.stripplot(data=ent,x='price',jitter= True ,orient ='v',size=6,color='#ff8300')
plt.title('Entertainment',fontsize=fsize)
plt.xlabel('')

plt.subplot(4,1,3)
plt.xlim(yrange)
edu = paidapps[paidapps.prime_genre=='Education']
sns.stripplot(data=edu,x='price',jitter= True ,orient ='v' ,size=6,color='#20B2AA')
plt.title('Education',fontsize=fsize)
plt.xlabel('')

plt.subplot(4,1,4)
plt.xlim(yrange)
pv = paidapps[paidapps.prime_genre=='Photo & Video']
sns.stripplot(data=pv,x='price',jitter= True  ,orient ='v',size=6,color='#b84efd')
plt.title('Photo & Video',fontsize=fsize)
plt.xlabel('')

plt.show()

分类方式


s = data.prime_genre.value_counts().index[:4]
def categ(x):
    if x in s:
        return x
    else :
        return "Others"

data['broad_genre']= data.prime_genre.apply(lambda x : categ(x))

free = data[data.price==0].broad_genre.value_counts().sort_index().to_frame()
paid = data[data.price>0].broad_genre.value_counts().sort_index().to_frame()
total = data.broad_genre.value_counts().sort_index().to_frame()
free.columns=['free']
paid.columns=['paid']
total.columns=['total']
dist = free.join(paid).join(total)
dist ['paid_per'] = dist.paid*100/dist.total
dist ['free_per'] = dist.free*100/dist.total
dist

BlueOrangeWapang = ['#fc910d','#fcb13e','#239cd3','#1674b1','#ed6d50']
plt.figure(figsize=(10,10))
label_names=data.broad_genre.value_counts().sort_index().index
size = data.broad_genre.value_counts().sort_index().tolist()
my_circle=plt.Circle( (0,0), 0.5, color='white')
plt.pie(size, labels=label_names, colors=BlueOrangeWapang)
p=plt.gcf()
p.gca().add_artist(my_circle)
plt.show()

plt.figure(figsize=(10,10))
f=pd.DataFrame(index=np.arange(0,10,2),data=dist.free.values,columns=['num'])
p=pd.DataFrame(index=np.arange(1,11,2),data=dist.paid.values,columns=['num'])
final = pd.concat([f,p],names=['labels']).sort_index()
final.num.tolist()

plt.figure(figsize=(20,20))
group_names=data.broad_genre.value_counts().sort_index().index
group_size=data.broad_genre.value_counts().sort_index().tolist()
h = ['Free', 'Paid']
subgroup_names= 5*h
sub= ['#45cea2','#fdd470']
subcolors= 5*sub
subgroup_size=final.num.tolist()


# First Ring (outside)
fig, ax = plt.subplots()
ax.axis('equal')
mypie, _ = ax.pie(group_size, radius=2.5, labels=group_names, colors=BlueOrangeWapang)
plt.setp( mypie, width=1.2, edgecolor='white')

# Second Ring (Inside)
mypie2, _ = ax.pie(subgroup_size, radius=1.6, labels=subgroup_names, labeldistance=0.7, colors=subcolors)
plt.setp( mypie2, width=0.8, edgecolor='white')
plt.margins(0,0)

# show it
plt.show()